LensNet: Enhancing Real-time Microlensing Event Discovery with Recurrent Neural Networks in the Korea Microlensing Telescope Network
Traditional microlensing event vetting methods require highly trained human experts, and the process is both complex and time consuming. This reliance on manual inspection often leads to inefficiencies and constrains the ability to scale for widespread exoplanet detection, ultimately hindering disco...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IOP Publishing
2025-01-01
|
| Series: | The Astronomical Journal |
| Subjects: | |
| Online Access: | https://doi.org/10.3847/1538-3881/ada4b5 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850229442654240768 |
|---|---|
| author | Javier Viaña Kyu-Ha Hwang Zoë de Beurs Jennifer C. Yee Andrew Vanderburg Michael D. Albrow Sun-Ju Chung Andrew Gould Cheongho Han Youn Kil Jung Yoon-Hyun Ryu In-Gu Shin Yossi Shvartzvald Hongjing Yang Weicheng Zang Sang-Mok Cha Dong-Jin Kim Seung-Lee Kim Chung-Uk Lee Dong-Joo Lee Yongseok Lee Byeong-Gon Park Richard W. Pogge |
| author_facet | Javier Viaña Kyu-Ha Hwang Zoë de Beurs Jennifer C. Yee Andrew Vanderburg Michael D. Albrow Sun-Ju Chung Andrew Gould Cheongho Han Youn Kil Jung Yoon-Hyun Ryu In-Gu Shin Yossi Shvartzvald Hongjing Yang Weicheng Zang Sang-Mok Cha Dong-Jin Kim Seung-Lee Kim Chung-Uk Lee Dong-Joo Lee Yongseok Lee Byeong-Gon Park Richard W. Pogge |
| author_sort | Javier Viaña |
| collection | DOAJ |
| description | Traditional microlensing event vetting methods require highly trained human experts, and the process is both complex and time consuming. This reliance on manual inspection often leads to inefficiencies and constrains the ability to scale for widespread exoplanet detection, ultimately hindering discovery rates. To address the limits of traditional microlensing event vetting, we have developed LensNet, a machine learning pipeline specifically designed to distinguish legitimate microlensing events from false positives caused by instrumental artifacts, such as pixel bleed trails and diffraction spikes. Our system operates in conjunction with a preliminary algorithm that detects increasing trends in flux. These flagged instances are then passed to LensNet for further classification, allowing for timely alerts and follow-up observations. Tailored for the multiobservatory setup of the Korea Microlensing Telescope Network and trained on a rich data set of manually classified events, LensNet is optimized for early detection and warning of microlensing occurrences, enabling astronomers to organize follow-up observations promptly. The internal model of the pipeline employs a multibranch Recurrent Neural Network architecture that evaluates time-series flux data with contextual information, including sky background, the full width at half-maximum of the target star, flux errors, point-spread function quality flags, and air mass for each observation. We demonstrate a classification accuracy above 87.5% and anticipate further improvements as we expand our training set and continue to refine the algorithm. |
| format | Article |
| id | doaj-art-74bdc1f9079e4432a4db48b973946eca |
| institution | OA Journals |
| issn | 1538-3881 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IOP Publishing |
| record_format | Article |
| series | The Astronomical Journal |
| spelling | doaj-art-74bdc1f9079e4432a4db48b973946eca2025-08-20T02:04:14ZengIOP PublishingThe Astronomical Journal1538-38812025-01-01169315910.3847/1538-3881/ada4b5LensNet: Enhancing Real-time Microlensing Event Discovery with Recurrent Neural Networks in the Korea Microlensing Telescope NetworkJavier Viaña0https://orcid.org/0000-0002-0563-784XKyu-Ha Hwang1https://orcid.org/0000-0002-9241-4117Zoë de Beurs2https://orcid.org/0000-0002-7564-6047Jennifer C. Yee3https://orcid.org/0000-0001-9481-7123Andrew Vanderburg4https://orcid.org/0000-0001-7246-5438Michael D. Albrow5https://orcid.org/0000-0003-3316-4012Sun-Ju Chung6https://orcid.org/0000-0001-6285-4528Andrew Gould7Cheongho Han8https://orcid.org/0000-0002-2641-9964Youn Kil Jung9https://orcid.org/0000-0002-0314-6000Yoon-Hyun Ryu10https://orcid.org/0000-0001-9823-2907In-Gu Shin11https://orcid.org/0000-0002-4355-9838Yossi Shvartzvald12https://orcid.org/0000-0003-1525-5041Hongjing Yang13https://orcid.org/0000-0003-0626-8465Weicheng Zang14https://orcid.org/0000-0001-6000-3463Sang-Mok Cha15https://orcid.org/0000-0002-7511-2950Dong-Jin Kim16Seung-Lee Kim17https://orcid.org/0000-0003-0562-5643Chung-Uk Lee18https://orcid.org/0000-0003-0043-3925Dong-Joo Lee19https://orcid.org/0009-0000-5737-0908Yongseok Lee20https://orcid.org/0000-0001-7594-8072Byeong-Gon Park21https://orcid.org/0000-0002-6982-7722Richard W. Pogge22https://orcid.org/0000-0003-1435-3053Department of Physics, Massachusetts Institute of Technology , Cambridge, MA 02139, USA ; vianajr@mit.edu; Kavli Institute for Astrophysics and Space Research, Massachusetts Institute of Technology , Cambridge, MA 02139, USAKorea Astronomy and Space Science Institute , Daejeon 34055, Republic of Korea ; kyuha@kasi.re.krDepartment of Physics, Massachusetts Institute of Technology , Cambridge, MA 02139, USA ; vianajr@mit.edu; Kavli Institute for Astrophysics and Space Research, Massachusetts Institute of Technology , Cambridge, MA 02139, USA; Department of Earth, Atmospheric and Planetary Sciences, Massachusetts Institute of Technology , Cambridge, MA 02139, USACenter for Astrophysics ∣ Harvard & Smithsonian , 60 Garden St., Cambridge, MA 02138, USA ; jyee@cfa.harvard.eduDepartment of Physics, Massachusetts Institute of Technology , Cambridge, MA 02139, USA ; vianajr@mit.edu; Kavli Institute for Astrophysics and Space Research, Massachusetts Institute of Technology , Cambridge, MA 02139, USAUniversity of Canterbury , School of Physical and Chemical Sciences, Private Bag 4800, Christchurch 8020, New ZealandKorea Astronomy and Space Science Institute , Daejeon 34055, Republic of Korea ; kyuha@kasi.re.krMax-Planck-Institute for Astronomy , Königstuhl 17, 69117 Heidelberg, Germany; Department of Astronomy, Ohio State University , 140 W. 18th Ave., Columbus, OH 43210, USADepartment of Physics, Chungbuk National University , Cheongju 28644, Republic of KoreaKorea Astronomy and Space Science Institute , Daejeon 34055, Republic of Korea ; kyuha@kasi.re.kr; National University of Science and Technology (UST) , Daejeon 34113, Republic of KoreaKorea Astronomy and Space Science Institute , Daejeon 34055, Republic of Korea ; kyuha@kasi.re.krCenter for Astrophysics ∣ Harvard & Smithsonian , 60 Garden St., Cambridge, MA 02138, USA ; jyee@cfa.harvard.eduDepartment of Particle Physics and Astrophysics, Weizmann Institute of Science , Rehovot 7610001, IsraelDepartment of Astronomy, Tsinghua University , Beijing 100084, People's Republic of ChinaCenter for Astrophysics ∣ Harvard & Smithsonian , 60 Garden St., Cambridge, MA 02138, USA ; jyee@cfa.harvard.eduKorea Astronomy and Space Science Institute , Daejeon 34055, Republic of Korea ; kyuha@kasi.re.kr; School of Space Research, Kyung Hee University , Yongin, Kyeonggi 17104, Republic of KoreaKorea Astronomy and Space Science Institute , Daejeon 34055, Republic of Korea ; kyuha@kasi.re.krKorea Astronomy and Space Science Institute , Daejeon 34055, Republic of Korea ; kyuha@kasi.re.krKorea Astronomy and Space Science Institute , Daejeon 34055, Republic of Korea ; kyuha@kasi.re.krKorea Astronomy and Space Science Institute , Daejeon 34055, Republic of Korea ; kyuha@kasi.re.krKorea Astronomy and Space Science Institute , Daejeon 34055, Republic of Korea ; kyuha@kasi.re.kr; School of Space Research, Kyung Hee University , Yongin, Kyeonggi 17104, Republic of KoreaKorea Astronomy and Space Science Institute , Daejeon 34055, Republic of Korea ; kyuha@kasi.re.krDepartment of Astronomy, Ohio State University , 140 West 18th Ave., Columbus, OH 43210, USA; Center for Cosmology and AstroParticle Physics, Ohio State University , 191 West Woodruff Ave., Columbus, OH 43210, USATraditional microlensing event vetting methods require highly trained human experts, and the process is both complex and time consuming. This reliance on manual inspection often leads to inefficiencies and constrains the ability to scale for widespread exoplanet detection, ultimately hindering discovery rates. To address the limits of traditional microlensing event vetting, we have developed LensNet, a machine learning pipeline specifically designed to distinguish legitimate microlensing events from false positives caused by instrumental artifacts, such as pixel bleed trails and diffraction spikes. Our system operates in conjunction with a preliminary algorithm that detects increasing trends in flux. These flagged instances are then passed to LensNet for further classification, allowing for timely alerts and follow-up observations. Tailored for the multiobservatory setup of the Korea Microlensing Telescope Network and trained on a rich data set of manually classified events, LensNet is optimized for early detection and warning of microlensing occurrences, enabling astronomers to organize follow-up observations promptly. The internal model of the pipeline employs a multibranch Recurrent Neural Network architecture that evaluates time-series flux data with contextual information, including sky background, the full width at half-maximum of the target star, flux errors, point-spread function quality flags, and air mass for each observation. We demonstrate a classification accuracy above 87.5% and anticipate further improvements as we expand our training set and continue to refine the algorithm.https://doi.org/10.3847/1538-3881/ada4b5Gravitational microlensingGravitational microlensing exoplanet detectionNeural networksClassification |
| spellingShingle | Javier Viaña Kyu-Ha Hwang Zoë de Beurs Jennifer C. Yee Andrew Vanderburg Michael D. Albrow Sun-Ju Chung Andrew Gould Cheongho Han Youn Kil Jung Yoon-Hyun Ryu In-Gu Shin Yossi Shvartzvald Hongjing Yang Weicheng Zang Sang-Mok Cha Dong-Jin Kim Seung-Lee Kim Chung-Uk Lee Dong-Joo Lee Yongseok Lee Byeong-Gon Park Richard W. Pogge LensNet: Enhancing Real-time Microlensing Event Discovery with Recurrent Neural Networks in the Korea Microlensing Telescope Network The Astronomical Journal Gravitational microlensing Gravitational microlensing exoplanet detection Neural networks Classification |
| title | LensNet: Enhancing Real-time Microlensing Event Discovery with Recurrent Neural Networks in the Korea Microlensing Telescope Network |
| title_full | LensNet: Enhancing Real-time Microlensing Event Discovery with Recurrent Neural Networks in the Korea Microlensing Telescope Network |
| title_fullStr | LensNet: Enhancing Real-time Microlensing Event Discovery with Recurrent Neural Networks in the Korea Microlensing Telescope Network |
| title_full_unstemmed | LensNet: Enhancing Real-time Microlensing Event Discovery with Recurrent Neural Networks in the Korea Microlensing Telescope Network |
| title_short | LensNet: Enhancing Real-time Microlensing Event Discovery with Recurrent Neural Networks in the Korea Microlensing Telescope Network |
| title_sort | lensnet enhancing real time microlensing event discovery with recurrent neural networks in the korea microlensing telescope network |
| topic | Gravitational microlensing Gravitational microlensing exoplanet detection Neural networks Classification |
| url | https://doi.org/10.3847/1538-3881/ada4b5 |
| work_keys_str_mv | AT javierviana lensnetenhancingrealtimemicrolensingeventdiscoverywithrecurrentneuralnetworksinthekoreamicrolensingtelescopenetwork AT kyuhahwang lensnetenhancingrealtimemicrolensingeventdiscoverywithrecurrentneuralnetworksinthekoreamicrolensingtelescopenetwork AT zoedebeurs lensnetenhancingrealtimemicrolensingeventdiscoverywithrecurrentneuralnetworksinthekoreamicrolensingtelescopenetwork AT jennifercyee lensnetenhancingrealtimemicrolensingeventdiscoverywithrecurrentneuralnetworksinthekoreamicrolensingtelescopenetwork AT andrewvanderburg lensnetenhancingrealtimemicrolensingeventdiscoverywithrecurrentneuralnetworksinthekoreamicrolensingtelescopenetwork AT michaeldalbrow lensnetenhancingrealtimemicrolensingeventdiscoverywithrecurrentneuralnetworksinthekoreamicrolensingtelescopenetwork AT sunjuchung lensnetenhancingrealtimemicrolensingeventdiscoverywithrecurrentneuralnetworksinthekoreamicrolensingtelescopenetwork AT andrewgould lensnetenhancingrealtimemicrolensingeventdiscoverywithrecurrentneuralnetworksinthekoreamicrolensingtelescopenetwork AT cheonghohan lensnetenhancingrealtimemicrolensingeventdiscoverywithrecurrentneuralnetworksinthekoreamicrolensingtelescopenetwork AT younkiljung lensnetenhancingrealtimemicrolensingeventdiscoverywithrecurrentneuralnetworksinthekoreamicrolensingtelescopenetwork AT yoonhyunryu lensnetenhancingrealtimemicrolensingeventdiscoverywithrecurrentneuralnetworksinthekoreamicrolensingtelescopenetwork AT ingushin lensnetenhancingrealtimemicrolensingeventdiscoverywithrecurrentneuralnetworksinthekoreamicrolensingtelescopenetwork AT yossishvartzvald lensnetenhancingrealtimemicrolensingeventdiscoverywithrecurrentneuralnetworksinthekoreamicrolensingtelescopenetwork AT hongjingyang lensnetenhancingrealtimemicrolensingeventdiscoverywithrecurrentneuralnetworksinthekoreamicrolensingtelescopenetwork AT weichengzang lensnetenhancingrealtimemicrolensingeventdiscoverywithrecurrentneuralnetworksinthekoreamicrolensingtelescopenetwork AT sangmokcha lensnetenhancingrealtimemicrolensingeventdiscoverywithrecurrentneuralnetworksinthekoreamicrolensingtelescopenetwork AT dongjinkim lensnetenhancingrealtimemicrolensingeventdiscoverywithrecurrentneuralnetworksinthekoreamicrolensingtelescopenetwork AT seungleekim lensnetenhancingrealtimemicrolensingeventdiscoverywithrecurrentneuralnetworksinthekoreamicrolensingtelescopenetwork AT chunguklee lensnetenhancingrealtimemicrolensingeventdiscoverywithrecurrentneuralnetworksinthekoreamicrolensingtelescopenetwork AT dongjoolee lensnetenhancingrealtimemicrolensingeventdiscoverywithrecurrentneuralnetworksinthekoreamicrolensingtelescopenetwork AT yongseoklee lensnetenhancingrealtimemicrolensingeventdiscoverywithrecurrentneuralnetworksinthekoreamicrolensingtelescopenetwork AT byeonggonpark lensnetenhancingrealtimemicrolensingeventdiscoverywithrecurrentneuralnetworksinthekoreamicrolensingtelescopenetwork AT richardwpogge lensnetenhancingrealtimemicrolensingeventdiscoverywithrecurrentneuralnetworksinthekoreamicrolensingtelescopenetwork |